FreeCHROMA: Generative Chroma Keying from Unaligned Background References
cs.CV
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- RelightVid: Temporal-Consistent Diffusion Model for Video Relighting
- PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
- LoRA: Low-Rank Adaptation of Large Language Models
- Bernini: Latent Semantic Planning for Video Diffusion
- OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
- Wan: Open and Advanced Large-Scale Video Generative Models
- ID-V2V: Identity-Preserving Video Restylization
- Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models
- VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models